Endpoint-aligned artificial intelligence for biopsy-sparing assessment of suspected basal cell carcinoma
Preprint
Abstract
Basal cell carcinoma (BCC) care follows a sequence of decisions from triage to pathological subtyping and depth assessment, and the information available changes at each step. To date, no artificial-intelligence (AI) tool using non-invasive inputs has been developed to support this full decision-making sequence. In this study, we developed a multi-endpoint AI framework matching non-invasive inputs to each decision point in 1,459 internal and 995 external patients. Triage macro-AUROC was 0.995 internally, 0.978 externally and 0.853 in a geographically distinct cohort, with risk stratification 0.943 and 0.899. For thickness, the highest-precision configuration used dermoscopy alone rather than all modalities (0.949 versus 0.881). Performance exceeded the 19-dermatologist mean on matched cases for every prespecified primary metric (all P ≤ 0.014). Local adaptation raised in-scope accuracy from 0.790 to 0.954 but shifted action-proxy routing toward the no-further-assessment classes for out-of-scope inputs, reducing sensitivity from 0.953 to 0.697. A validation-locked Mahalanobis gate enriched sensitivity among accepted cases to 0.775 at 0.791 coverage but only partially mitigated residual out-of-scope routing errors. These findings separate closed-set performance from scope control and support endpoint-specific validation of biopsy-sparing AI for BCC diagnosis and personalized treatment planning.Keywords
Funding Information
- National Natural Science Foundation of China (82404139)
- the Shaanxi Province Key Industrial Innovation Chain (2024SF-ZDCYL-01-14)
- the Innovation Capability Support Program of Shaanxi Province (2022TD-48)
This publication has 27 references indexed in Scilit:
- Comparative and complementary diagnostic value of dermatoscopy and clinical close-up photography in skin cancer diagnosis: A study from the MILK10k datasetJournal of the American Academy of Dermatology, 2026
- Current landscape of AI Regulation in DermatologyJournal of the American Academy of Dermatology, 2025
- Pre-trained multimodal large language model enhances dermatological diagnosis using SkinGPT-4Nature Communications, 2024
- Detection and subtyping of basal cell carcinoma in whole-slide histopathology using weakly-supervised learningMedical Image Analysis, 2023
- European consensus-based interdisciplinary guideline for diagnosis and treatment of basal cell carcinoma—update 2023European Journal of Cancer, 2023
- PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphonesData in Brief, 2020
- The diagnostic accuracy of dermoscopy for basal cell carcinoma: A systematic review and meta-analysisJournal of the American Academy of Dermatology, 2019
- Basal cell carcinomaJournal of the American Academy of Dermatology, 2019
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- A well-conditioned estimator for large-dimensional covariance matricesJournal of Multivariate Analysis, 2004